# Action-relation hallucination evaluation on MMRel Real Source: [Action-relation hallucination evaluation on MMRel Real]() Collection index: [llms.txt]() Data updated: 2026-05-13T09:44:15.801Z Evaluation of model performance on Action-relation hallucination using the MMRel Real dataset, measured by Accuracy and F1 score. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Action-relation hallucination evaluation | | Dataset (including any stated split) | MMRel Real | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 25 of 25 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Accuracy](): Higher is better; unit: PERCENT. - [F1 Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | RVE | 78.56 | Not recorded | 6a040599dbc836b87d827562 | | RVE | 78.36 | Not recorded | 6a040599dbc836b87d827562 | | RVE | 78.08 | Not recorded | 6a040599dbc836b87d827562 | | RVE | 77.39 | Not recorded | 6a040599dbc836b87d827562 | | RVE | 76.44 | Not recorded | 6a040599dbc836b87d827562 | | Vanilla | 74.51 | Not recorded | 6a040599dbc836b87d827562 | | ICD | 74.06 | Not recorded | 6a040599dbc836b87d827562 | | ICD | 73.3 | Not recorded | 6a040599dbc836b87d827562 | | VCD | 73.15 | Not recorded | 6a040599dbc836b87d827562 | | Vanilla | 72.96 | Not recorded | 6a040599dbc836b87d827562 | | VAF | 72.52 | Not recorded | 6a040599dbc836b87d827562 | | ICD | 72.31 | Not recorded | 6a040599dbc836b87d827562 | | VCD | 71.8 | Not recorded | 6a040599dbc836b87d827562 | | Vanilla | 71.12 | Not recorded | 6a040599dbc836b87d827562 | | ICD | 70.79 | Not recorded | 6a040599dbc836b87d827562 | | Vanilla | 70.58 | Not recorded | 6a040599dbc836b87d827562 | | VAF | 69.84 | Not recorded | 6a040599dbc836b87d827562 | | VAF | 69.62 | Not recorded | 6a040599dbc836b87d827562 | | VCD | 68.97 | Not recorded | 6a040599dbc836b87d827562 | | VCD | 68.86 | Not recorded | 6a040599dbc836b87d827562 | | VAF | 68.02 | Not recorded | 6a040599dbc836b87d827562 | | Vanilla | 65.47 | Not recorded | 6a040599dbc836b87d827562 | | VCD | 64.67 | Not recorded | 6a040599dbc836b87d827562 | | VAF | 62.7 | Not recorded | 6a040599dbc836b87d827562 | | ICD | 61.1 | Not recorded | 6a040599dbc836b87d827562 | ### RVE Accuracy: 78.56. Result ID: 6a0446cb47f34ce924ea8254. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LVLM Model":"InstructBLIP-7B"}. This record does not assert independent reproduction. ### RVE Accuracy: 78.36. Result ID: 6a0446cb47f34ce924ea825e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LVLM Model":"LLaVA-1.5-13B"}. This record does not assert independent reproduction. ### RVE Accuracy: 78.08. Result ID: 6a0446cb47f34ce924ea824a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LVLM Model":"LLaVA-1.5-7B"}. This record does not assert independent reproduction. ### RVE Accuracy: 77.39. Result ID: 6a0446cb47f34ce924ea824f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LVLM Model":"LLaVA-NeXT-7B"}. This record does not assert independent reproduction. ### RVE Accuracy: 76.44. Result ID: 6a0446cb47f34ce924ea8259. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LVLM Model":"ShareGPT4V-7B"}. This record does not assert independent reproduction. ### Vanilla Accuracy: 74.51. Result ID: 6a0446cb47f34ce924ea825a. [Reporting paper]() Recorded evaluation configuration: {"LVLM Model":"LLaVA-1.5-13B"}. This record does not assert independent reproduction. ### ICD Accuracy: 74.06. Result ID: 6a0446cb47f34ce924ea825c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LVLM Model":"LLaVA-1.5-13B"}. This record does not assert independent reproduction. ### ICD Accuracy: 73.3. Result ID: 6a0446cb47f34ce924ea8248. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LVLM Model":"LLaVA-1.5-7B"}. This record does not assert independent reproduction. ### VCD Accuracy: 73.15. Result ID: 6a0446cb47f34ce924ea8256. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LVLM Model":"ShareGPT4V-7B"}. This record does not assert independent reproduction. ### Vanilla Accuracy: 72.96. Result ID: 6a0446cb47f34ce924ea8255. [Reporting paper]() Recorded evaluation configuration: {"LVLM Model":"ShareGPT4V-7B"}. This record does not assert independent reproduction. ### VAF Accuracy: 72.52. Result ID: 6a0446cb47f34ce924ea825d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"LVLM Model":"LLaVA-1.5-13B"}. This record does not assert independent reproduction. ### ICD Accuracy: 72.31. Result ID: 6a0446cb47f34ce924ea8257. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LVLM Model":"ShareGPT4V-7B"}. This record does not assert independent reproduction. ### VCD Accuracy: 71.8. Result ID: 6a0446cb47f34ce924ea825b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LVLM Model":"LLaVA-1.5-13B"}. This record does not assert independent reproduction. ### Vanilla Accuracy: 71.12. Result ID: 6a0446cb47f34ce924ea8246. [Reporting paper]() Recorded evaluation configuration: {"LVLM Model":"LLaVA-1.5-7B"}. This record does not assert independent reproduction. ### ICD Accuracy: 70.79. Result ID: 6a0446cb47f34ce924ea824d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LVLM Model":"LLaVA-NeXT-7B"}. This record does not assert independent reproduction. ### Vanilla Accuracy: 70.58. Result ID: 6a0446cb47f34ce924ea824b. [Reporting paper]() Recorded evaluation configuration: {"LVLM Model":"LLaVA-NeXT-7B"}. This record does not assert independent reproduction. ### VAF Accuracy: 69.84. Result ID: 6a0446cb47f34ce924ea8258. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"LVLM Model":"ShareGPT4V-7B"}. This record does not assert independent reproduction. ### VAF Accuracy: 69.62. Result ID: 6a0446cb47f34ce924ea824e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"LVLM Model":"LLaVA-NeXT-7B"}. This record does not assert independent reproduction. ### VCD Accuracy: 68.97. Result ID: 6a0446cb47f34ce924ea8251. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LVLM Model":"InstructBLIP-7B"}. This record does not assert independent reproduction. ### VCD Accuracy: 68.86. Result ID: 6a0446cb47f34ce924ea824c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LVLM Model":"LLaVA-NeXT-7B"}. This record does not assert independent reproduction. ### VAF Accuracy: 68.02. Result ID: 6a0446cb47f34ce924ea8249. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"LVLM Model":"LLaVA-1.5-7B"}. This record does not assert independent reproduction. ### Vanilla Accuracy: 65.47. Result ID: 6a0446cb47f34ce924ea8250. [Reporting paper]() Recorded evaluation configuration: {"LVLM Model":"InstructBLIP-7B"}. This record does not assert independent reproduction. ### VCD Accuracy: 64.67. Result ID: 6a0446cb47f34ce924ea8247. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LVLM Model":"LLaVA-1.5-7B"}. This record does not assert independent reproduction. ### VAF Accuracy: 62.7. Result ID: 6a0446cb47f34ce924ea8253. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"LVLM Model":"InstructBLIP-7B"}. This record does not assert independent reproduction. ### ICD Accuracy: 61.1. Result ID: 6a0446cb47f34ce924ea8252. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LVLM Model":"InstructBLIP-7B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.